GitHub Trends

#python#large_language_models#llms#long_video_understanding#multi_modal_llms#rag#retrieval_augmented_generation Vimo is a desktop app that lets me chat with any video, from short clips to hundreds of hours, in simple natural language. I can drag and drop videos, ask questions, find exact moments, compare multiple videos, and export useful insights, all on macOS, Windows, or Linux. Powering this is the VideoRAG algorithm, which deeply understands visual, audio, and contextual information, giving accurate answers even for very long videos. This helps me save time, understand complex content faster, and turn large video libraries into searchable, usable knowledge. https://github.com/HKUDS/VideoRAG

#python#ai#faiss#gpt_oss#langchain#llama_index#llm#localstorage#offline_first#ollama#privacy#python#rag#retrieval_augmented_generation#vector_database#vector_search#vectors LEANN is a tiny, powerful vector database that lets you turn your laptop into a personal AI assistant capable of searching millions of documents using 97% less storage than traditional systems without losing accuracy. It works by storing a compact graph and computing embeddings only when needed, saving huge space and keeping your data private on your device. You can search your files, emails, browser history, chat logs, live data from platforms like Slack and Twitter, and even codebases—all locally without cloud costs. This means fast, private, and efficient AI-powered search and retrieval on your own laptop. https://github.com/yichuan-w/LEANN

#python#ai#context#embedded#faiss#knowledge_base#knowledge_graph#llm#machine_learning#memory#nlp#offline_first#opencv#python#rag#retrieval_augmented_generation#semantic_search#vector_database#video_processing Memvid lets you store millions of text pieces inside a single MP4 video file using QR codes, making your data 50-100 times smaller than usual databases. You can search this video instantly in under 100 milliseconds without needing servers or internet after setup. It works offline, is easy to use with simple Python code, and supports PDFs and chat with your data. The upcoming version 2 will add features like continuous memory updates, shareable capsules, fast local caching, and better video compression, making your AI memory smarter, faster, and more flexible. This means you get a powerful, portable, and efficient way to manage and search huge knowledge bases quickly and easily. https://github.com/Olow304/memvid

#python#multi_modal_rag#retrieval_augmented_generation RAG-Anything is a powerful AI system that helps you search and understand documents containing mixed content like text, images, tables, and math formulas all in one place. It uses smart parsing and analysis to break down complex documents and builds a knowledge graph to connect different types of information. This means you can ask detailed questions about any part of a document—whether text or images—and get clear, accurate answers quickly. It supports many file types like PDFs and Office files, making it ideal for research, technical work, or business reports where you need a unified, easy way to explore rich, multimodal content. This saves you time and effort by avoiding multiple tools and gives you deeper insights from your documents. https://github.com/HKUDS/RAG-Anything

#python#agents#generative_ai_tools#llamacpp#llm#onnx#openvino#parsing#retrieval_augmented_generation#small_specialized_models llmware is a powerful, easy-to-use platform that helps you build AI applications using small, specialized language models designed for business tasks like question-answering, summarization, and data extraction. It supports private, secure deployment on your own machines without needing expensive GPUs, making it cost-effective and safe for enterprise use. You can organize and search your documents, run smart queries, and combine knowledge with AI to get accurate answers quickly. It also offers many ready-to-use models and examples, plus tools for building chatbots and agents that automate complex workflows. This helps you save time, improve accuracy, and securely leverage AI for your business needs[1][3][5]. https://github.com/llmware-ai/llmware

#python#agent_computer_interface#ai_agents#computer_automation#computer_use#grounding#gui_agents#in_context_reinforcement_learning#memory#mllm#planning#retrieval_augmented_generation Agent S2 is a smart AI assistant that handles computer tasks by breaking them into smaller steps and using specialized tools for each part, making it highly adaptable and efficient across different systems like Windows and Android. It outperforms other AI tools in completing complex tasks, learns from experience, and adjusts plans as needed, helping users automate digital work more reliably and effectively. https://github.com/simular-ai/Agent-S